Electric parameter dynamic tracking based power consumption anomaly detection device and method

Abstract

The application discloses electric parameter dynamic tracking-based electric abnormality detection equipment and method, and particularly relates to the electric monitoring technical field, the method comprises the following steps: acquiring the electric parameter data stream of the nth electric equipment in the target area, the electric parameter data stream comprises current value, voltage value, active power and reactive power; acquiring instantaneous detection data based on the electric parameter data stream, analyzing the instantaneous detection data, and judging whether to mark the electric equipment as short-time abnormal electric consumption; acquiring harmonic detection data based on the electric parameter data stream, analyzing the harmonic detection data, and judging whether to mark the electric equipment as harmonic abnormal electric consumption; acquiring long-term detection data based on the electric parameter data stream, analyzing the long-term detection data, and judging whether to mark the electric equipment as long-term abnormal electric consumption; the application not only improves the intelligent level of abnormal electric consumption detection, but also continuously optimizes the prediction effect through model training, and realizes automatic and accurate analysis of abnormal electric consumption.

Description

Technical Field

[0001] This invention relates to the field of electricity monitoring technology, and more specifically, to an electricity anomaly detection device and method based on dynamic tracking of electrical parameters. Background Technology

[0002] With the continuous expansion of electricity consumption and the increasing diversification of electrical equipment, the detection of abnormal electricity usage faces numerous challenges. Traditional electricity detection mainly relies on simple threshold settings, such as judging whether the current and voltage amplitudes exceed limits. However, in reality, the operating states of electrical equipment are complex, and electrical parameters change dynamically during normal operation. For example, large motors in factories experience a significant surge in current at startup, followed by a drop after stabilization, and electrical parameters vary significantly under different operating conditions. Moreover, different specifications and types of equipment have different power consumption patterns, making it difficult for fixed thresholds to accurately distinguish between normal changes and abnormalities. At the same time, electricity theft is frequent, with sophisticated technical means used to interfere with meters or lines, causing subtle abnormal changes in electrical parameters that traditional detection methods are prone to missing. Furthermore, the development of smart grids has led to a massive increase in electricity data, urgently requiring accurate detection of this data.

[0003] Existing methods, for example, patent application CN111103497A discloses a detection device and method for abnormal user electricity consumption. The detection device includes a main station terminal installed at the starting point of a branch line and a portable terminal at the meter box inlet. The portable terminal scans the asset number of the electricity meter in the meter box, obtains the communication address, and forms an electricity meter file for each meter box. The main station terminal collects the voltage and current of the branch line, generates daily frozen data, and copies the daily frozen data and files of the portable terminal and its subordinate electricity meters. The main station terminal calculates the daily frozen energy increment and the user's energy increment to determine whether there is abnormal line loss in the branch line and meter box. While the above method improves the convenience of abnormal electricity consumption detection, research and application of the above method and existing technologies have revealed at least the following shortcomings:

[0004] The above methods judge abnormal line losses based solely on numerical comparisons rather than intelligent pattern recognition, making it difficult to analyze complex abnormal electricity consumption behaviors.

[0005] To this end, the present invention provides a device and method for detecting abnormal electricity consumption based on dynamic tracking of electrical parameters. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a power consumption anomaly detection device and method based on dynamic tracking of electrical parameters to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] In a first aspect, the present invention provides a method for detecting abnormal electricity consumption based on dynamic tracking of electrical parameters, comprising:

[0009] Acquire the electrical parameter data stream of the nth electrical device within the target area, wherein the electrical parameter data stream includes current value, voltage value, active power and reactive power;

[0010] Instantaneous detection data is acquired based on electrical parameter data streams, and the instantaneous detection data is analyzed to determine whether to mark the electrical equipment as having short-term abnormal power consumption.

[0011] Harmonic detection data is acquired based on electrical parameter data streams, and the harmonic detection data is analyzed to determine whether to mark electrical equipment as having abnormal harmonic power consumption.

[0012] Long-term monitoring data is acquired based on electrical parameter data streams, and the long-term monitoring data is analyzed to determine whether to mark the electrical equipment as having long-term abnormal power consumption.

[0013] Abnormal power consumption characteristics are obtained from short-term abnormal power consumption, harmonic abnormal power consumption, and long-term abnormal power consumption. These abnormal characteristics are then input into a pre-built abnormal power consumption analysis model to obtain analysis results.

[0014] Furthermore, the instantaneous detection data includes instantaneous voltage, instantaneous current, and power factor;

[0015] Methods for analyzing instantaneous detection data include:

[0016] Step a1: Calculate the instantaneous current rate, instantaneous voltage rate, and real-time power factor using a sliding window. The calculation formula is as follows:

[0017] In the formula, ΔI represents the instantaneous current rate, ΔU represents the instantaneous voltage rate, Δt represents the time interval, PF represents the real-time power factor, P represents the active power, S represents the apparent power; I(t) represents the current value, and U(t) represents the voltage value.

[0018] Step a2: Set the instantaneous current rate threshold ΔI th Instantaneous voltage rate threshold ΔU th and the lower limit threshold of power factor (PF) th ;

[0019] The instantaneous current rate ΔI is compared with the instantaneous current rate threshold ΔI. th Comparing the instantaneous voltage rate ΔU with the instantaneous voltage rate threshold ΔU th The real-time power factor (PF) is compared with the lower limit threshold power factor (PF). th Compare;

[0020] If ΔI>ΔI th And ΔU < ΔUth And PF < PF th If so, the current electrical equipment will be marked as having short-term abnormal power consumption;

[0021] If ΔI≤ΔI th And ΔU ≥ ΔU th And PF≥PF th If so, no action will be taken on the current electrical equipment;

[0022] Step a3: Based on the short-term abnormal power consumption record, record the short-term timestamp and the sudden change in electrical parameter value.

[0023] Furthermore, the harmonic detection data includes current, voltage values, and harmonic distortion rate; the abnormal harmonic power consumption includes first harmonic abnormal power consumption and second harmonic abnormal power consumption.

[0024] Methods for analyzing harmonic detection data based on harmonic analysis include:

[0025] Step b1: Perform spectral analysis on the current value using Fast Fourier Transform to extract the harmonic component amplitude; the calculation formula is as follows:

[0026] H b =FFT(I(t)),b=1,2,3,...,B;

[0027] In the formula, H b This represents the amplitude of the b-th harmonic component, where B is the highest harmonic order.

[0028] Step b2: Based on the harmonic component amplitude H b The formula for calculating harmonic distortion rate is as follows:

[0029]

[0030] In the formula, THD represents the harmonic distortion rate, and H1 represents the amplitude of the first harmonic component;

[0031] Step b3: Set a preset distortion rate threshold. Compare the harmonic distortion rate with the preset distortion rate threshold. If the harmonic distortion rate is greater than or equal to the preset distortion rate threshold, mark the electrical equipment as having abnormal first harmonic power consumption. If the harmonic distortion rate is less than the preset distortion rate threshold, generate an analysis command.

[0032] Step b4: Receive the analysis command, obtain the harmonic characteristic coefficient, compare the harmonic characteristic coefficient with the preset first coefficient threshold, and determine whether to mark the electrical equipment as having abnormal second harmonic power consumption.

[0033] Step b5: Record the abnormal electrical parameters and timestamps of the harmonics based on the abnormal power consumption of the first or second harmonic.

[0034] Furthermore, methods for obtaining harmonic characteristic coefficients include:

[0035] Step b41: Obtain harmonic characteristic data, which includes harmonic component amplitude, harmonic distortion rate, and harmonic duration;

[0036] Step b42: Normalize the harmonic characteristic data and calculate the harmonic characteristic coefficients. The calculation formula is as follows:

[0037] XBT=H b ×XB1+THD×XB2+Sj×XB3;

[0038] In the formula, XBT represents the harmonic characteristic coefficient, Sj represents the harmonic duration, and XB1, XB2 and XB3 are weighting factors.

[0039] Furthermore, methods for determining whether to mark electrical equipment as having abnormal second harmonic power consumption include:

[0040] If the harmonic characteristic coefficient is greater than or equal to the preset first coefficient threshold, the electrical equipment will be marked as having abnormal second harmonic power consumption.

[0041] If the harmonic characteristic coefficient is less than the preset first coefficient threshold, no action will be taken on the electrical equipment.

[0042] Furthermore, the method for obtaining the harmonic duration includes:

[0043] Set a harmonic distortion rate threshold. When THD is greater than or equal to the set harmonic distortion rate threshold, the recording start time is t1. When THD is less than the set harmonic distortion rate threshold, the recording end time is t2.

[0044] The harmonic duration is calculated using the formula Sj = t2 - t1;

[0045] Methods for determining whether to mark electrical equipment as having abnormal second harmonic power consumption also include:

[0046] Multiple sets of fingerprint feature data recorded by historical electricity theft devices are pre-stored in the harmonic fingerprint database to form matching templates;

[0047] The matching template is: device type - harmonic component amplitude - harmonic distortion rate - harmonic duration;

[0048] Harmonic feature data and fingerprint feature data are matched for similarity to obtain similarity values;

[0049] A preset similarity threshold is set. The similarity value is compared with the preset similarity threshold. If the similarity value is greater than or equal to the preset similarity threshold, the electrical equipment is marked as having abnormal second harmonic power consumption. If the similarity value is less than the preset similarity threshold, no action is taken on the electrical equipment.

[0050] Furthermore, the long-term monitoring data includes active power, reactive power, and power factor;

[0051] Methods for analyzing long-term monitoring data include:

[0052] Step c1: Extract the long-term load factor from the historical load monitoring process and mark it as the historical long-term load factor. Use the extracted historical long-term load factor to establish a load time series set. The load time series set includes i historical long-term load factors. The time interval of the i historical long-term load factors is equal. The i historical long-term load factors correspond to a long-term analysis period.

[0053] The method for obtaining the long-term load factor includes:

[0054] The long-term load factor is obtained by formulating the calculation of active power, reactive power, and power factor from long-term monitoring data. The calculation formula is as follows:

[0055]

[0056] In the formula, CFX represents the long-term load factor, and W represents reactive power.

[0057] Step c2: Input the historical long-term load factor from the load time series set into the load forecasting model to predict the long-term load factor at time T in the future.

[0058] Furthermore, methods for determining whether to mark electrical equipment as having long-term abnormal power consumption include:

[0059] Step d1: Calculate the predicted long-term load factor CFX at time T in the future. t+1 Compare with the preset load factor threshold FX;

[0060] Step d2: Determine whether to mark the electrical equipment at time T in the future;

[0061] If CFX t+1 If the value is ≥FX, then the electrical equipment at time T in the future will be marked as having long-term abnormal power consumption.

[0062] If CFX t+1 If <FX, then no action will be taken on the electrical equipment at time T, and monitoring of the electrical equipment at time T will continue.

[0063] Step d3: Based on the long-term abnormal electricity consumption records, long-term abnormal electrical parameter values ​​and long-term timestamps.

[0064] Furthermore, the abnormal feature data includes short-term timestamps and abrupt electrical parameter values ​​of short-term abnormal electricity consumption records, harmonic abnormal electrical parameter values ​​and harmonic timestamps of harmonic abnormal electricity consumption records, and long-term abnormal electrical parameter values ​​and long-term timestamps of long-term abnormal electricity consumption records; the analysis results include electricity theft, abnormal electricity consumption, equipment failures, and line failures;

[0065] The training method for the abnormal power consumption analysis model includes:

[0066] K sets of abnormal feature data are collected in advance, where K is an integer greater than 1. The corresponding prediction results are set for the abnormal feature data. Different letter labels are set for abnormal electricity use, equipment failure and line failure. The letter labels of the prediction results are marked as prediction labels. The abnormal feature data and the corresponding prediction labels are converted into a set of feature vectors.

[0067] Each set of feature vectors is used as input to the abnormal power consumption analysis model. The abnormal power consumption analysis model outputs a set of predicted labels corresponding to each set of abnormal feature data and uses the actual predicted labels corresponding to each set of abnormal feature data as the prediction target. The actual predicted labels are the pre-set predicted labels corresponding to the abnormal feature data. The training objective is to minimize the sum of prediction errors of all abnormal feature data. The abnormal power consumption analysis model is trained until the sum of prediction errors converges and then training stops. The abnormal power consumption analysis model is specifically a deep neural network model.

[0068] Secondly, the present invention provides an electrical anomaly detection device based on dynamic tracking of electrical parameters; the device includes:

[0069] The data acquisition module acquires the electrical parameter data stream of the nth electrical device in the target area. The electrical parameter data stream includes current value, voltage value, active power and reactive power.

[0070] The instantaneous detection module acquires instantaneous detection data based on electrical parameter data streams, analyzes the instantaneous detection data, and determines whether to mark the electrical equipment as having short-term abnormal power consumption.

[0071] The harmonic detection module acquires harmonic detection data based on electrical parameter data streams, analyzes the harmonic detection data, and determines whether to mark the electrical equipment as having abnormal harmonic power consumption.

[0072] The long-term monitoring module acquires long-term monitoring data based on electrical parameter data streams, analyzes the long-term monitoring data, and determines whether to mark the electrical equipment as having long-term abnormal power consumption.

[0073] The comprehensive analysis module obtains abnormal characteristic data based on short-term abnormal power consumption, harmonic abnormal power consumption, and long-term abnormal power consumption. The abnormal characteristic data is then input into a pre-built abnormal power consumption analysis model to obtain analysis results.

[0074] The technical effects and advantages of this invention are as follows:

[0075] By acquiring electrical parameter data streams such as current, voltage, active power, and reactive power of electrical equipment, and combining this with multi-level analysis including instantaneous detection, harmonic detection, and long-term monitoring, different types of abnormal electricity consumption behaviors can be quickly and accurately identified. Instantaneous detection can analyze instantaneous current, voltage rate, and power factor in real time through a sliding window to quickly identify short-term abnormal electricity consumption; harmonic detection, based on Fast Fourier Transform and harmonic feature analysis, can effectively capture harmonic anomalies caused by connected electricity theft devices; long-term monitoring combines historical load data and predictive models to provide early warnings of potential long-term abnormal electricity consumption problems. Through multi-dimensional detection methods, this method can not only identify electricity theft but also accurately classify equipment faults and line faults, improving the comprehensiveness and reliability of abnormal electricity consumption analysis. Attached Figure Description

[0076] Figure 1 This is a flowchart of the power consumption anomaly detection method based on dynamic tracking of electrical parameters in Example 1;

[0077] Figure 2 This is a flowchart of the method for analyzing harmonic detection data based on harmonic analysis in Example 1;

[0078] Figure 3 This is a flowchart of the method for analyzing long-term detection data in Example 1;

[0079] Figure 4 This is a schematic diagram of the power consumption anomaly detection device based on dynamic tracking of electrical parameters in Example 2. Detailed Implementation

[0080] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0081] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0082] It should be understood that although terms such as "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and a similar second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated items listed.

[0083] Example 1

[0084] Please see Figure 1 As shown in the figure, this embodiment discloses a method for detecting abnormal electricity consumption based on dynamic tracking of electrical parameters. The method includes:

[0085] Step 1: Obtain the electrical parameter data stream of the nth electrical device in the target area. The electrical parameter data stream includes current value, voltage value, active power and reactive power.

[0086] It should be noted that the target area can be the incoming end of a power line, a branch line end, or the user's electrical equipment end. This embodiment uses the user's electrical equipment as an example to describe the power anomaly detection method in detail. High-precision current transformers (CTs) and voltage transformers (PTs) are installed on the electrical equipment. High-frequency synchronous sampling technology is used to collect electrical parameter data, with a sampling frequency of 50-100Hz to ensure accurate capture of transient electrical parameter data. The collected electrical parameter data is converted into digital signals by a data acquisition module (ADC) and transmitted in real time to the system database through a communication interface (such as RS-485, Ethernet, or a wireless module). The data is recorded and stored in timestamp order, forming a continuous electrical parameter data stream, providing complete data support for subsequent short-term analysis, long-term analysis, and harmonic analysis.

[0087] Step 2: Obtain instantaneous detection data based on electrical parameter data stream, analyze the instantaneous detection data, and determine whether to mark the electrical equipment as having short-term abnormal power consumption.

[0088] It should be noted that the instantaneous detection data includes instantaneous voltage, instantaneous current, and power factor;

[0089] In practice, methods for analyzing instantaneous detection data include:

[0090] Step a1: Calculate the instantaneous current rate, instantaneous voltage rate, and real-time power factor using a sliding window. The calculation formula is as follows:

[0091] In the formula, ΔI represents the instantaneous current rate, ΔU represents the instantaneous voltage rate, Δt represents the time interval, PF represents the real-time power factor, P represents the active power, and S represents the apparent power.

[0092] The current value I(t) reflects the real-time current flowing through the electrical equipment; the voltage value U(t) measures the voltage across the electrical equipment; and the active power P represents the power that electrical energy is effectively converted into actual working power.

[0093] It should be noted that the unit of the time interval is seconds or minutes, which is set by those skilled in the art based on experience, and is not specifically limited here.

[0094] Step a2: Set the instantaneous current rate threshold ΔI th Instantaneous voltage rate threshold ΔU th and the lower limit threshold of power factor (PF) th ;

[0095] The instantaneous current rate ΔI is compared with the instantaneous current rate threshold ΔI. th Comparing the instantaneous voltage rate ΔU with the instantaneous voltage rate threshold ΔU th The real-time power factor (PF) is compared with the lower limit threshold power factor (PF). th Compare;

[0096] If ΔI>ΔI th And ΔU < ΔU th And PF < PF th If so, the current electrical equipment will be marked as having short-term abnormal power consumption;

[0097] If ΔI≤ΔI th And ΔU ≥ ΔU th And PF≥PF th If the current electrical equipment is not processed, it indicates that the electrical equipment has been normally disconnected from the line, and short-term analysis will continue.

[0098] Step a3: Based on the short-term abnormal power consumption record, record the short-term timestamp and the sudden change in electrical parameter value.

[0099] The abrupt electrical parameter values ​​refer to the abnormally changing parameters recorded during short-term analysis of electrical equipment, including instantaneous current change rate, instantaneous voltage change rate, and abnormal power factor values.

[0100] Step 3: Obtain harmonic detection data based on the electrical parameter data stream, analyze the harmonic detection data, and determine whether to mark the electrical equipment as having abnormal harmonic power consumption.

[0101] It should be noted that: harmonic detection data includes current, voltage values, and harmonic distortion rate; the abnormal harmonic power consumption includes first harmonic abnormal power consumption and second harmonic abnormal power consumption.

[0102] Please see Figure 2 As shown, in practice, the methods for analyzing harmonic detection data based on harmonic analysis include:

[0103] Step b1: Perform spectral analysis on the current value using Fast Fourier Transform to extract the harmonic component amplitude; the calculation formula is as follows:

[0104] H b =FFT(I(t)),b=1,2,3,...,B;

[0105] In the formula, H b Let B represent the amplitude of the b-th harmonic component, where B is the highest harmonic order, and FFT(·) is the Fast Fourier Transform algorithm.

[0106] For example, H2 represents the second harmonic, with a frequency twice the amplitude of the first harmonic component; H3 represents the third harmonic, with a frequency three times the amplitude of the first harmonic component, and so on.

[0107] Step b2: Based on the harmonic component amplitude H b The formula for calculating harmonic distortion rate is as follows:

[0108]

[0109] In the formula, THD represents the harmonic distortion rate, and H1 represents the amplitude of the first harmonic component.

[0110] Step b3: Set a preset distortion rate threshold. Compare the harmonic distortion rate with the preset distortion rate threshold. If the harmonic distortion rate is greater than or equal to the preset distortion rate threshold, mark the electrical equipment as having abnormal first harmonic power consumption. If the harmonic distortion rate is less than the preset distortion rate threshold, generate an analysis command.

[0111] It should be noted that the amplitude of the harmonic components increases with the increase of the harmonic order, which is an odd number. Electrical equipment in the target area can also be marked as having abnormal harmonic power consumption.

[0112] Step b4: Receive the analysis command, obtain the harmonic characteristic coefficient, compare the harmonic characteristic coefficient with the preset first coefficient threshold, and determine whether to mark the electrical equipment as having abnormal second harmonic power consumption.

[0113] Step b5: Record the abnormal electrical parameters and timestamps of the harmonics based on the abnormal power consumption of the first or second harmonic.

[0114] It should be noted that the abnormal harmonic electrical parameter values ​​refer to the abnormal harmonic characteristics recorded when performing harmonic analysis on electrical equipment, including the abnormal harmonic component amplitude, total harmonic distortion (THD) value, and related current and voltage values.

[0115] Specifically, the methods for obtaining harmonic characteristic coefficients include:

[0116] Step b41: Obtain harmonic characteristic data, which includes harmonic component amplitude, harmonic distortion rate, and harmonic duration;

[0117] It should be noted that the harmonic duration is obtained by recording electrical parameter data streams using a harmonic analyzer. Specifically, the method for obtaining the harmonic duration includes:

[0118] Set a harmonic distortion rate threshold. When THD is greater than or equal to the set harmonic distortion rate threshold, the recording start time is t1. When THD is less than the set harmonic distortion rate threshold, the recording end time is t2.

[0119] The duration of harmonics is calculated using the formula Sj = t2 - t1.

[0120] Step b42: Normalize the harmonic characteristic data and calculate the harmonic characteristic coefficients. The calculation formula is as follows:

[0121] XBT=H b ×XB1+THD×XB2+Sj×XB3;

[0122] In the formula, XBT represents the harmonic characteristic coefficient, Sj represents the harmonic duration, and XB1, XB2 and XB3 are weighting factors, which are all set by those skilled in the art based on experience.

[0123] In practice, methods for determining whether to mark electrical equipment as having abnormal second harmonic power consumption include:

[0124] If the harmonic characteristic coefficient is greater than or equal to the preset first coefficient threshold, the electrical equipment will be marked as having abnormal second harmonic power consumption.

[0125] If the harmonic characteristic coefficient is less than the preset first coefficient threshold, no action will be taken on the electrical equipment.

[0126] It should be noted that the first coefficient threshold is calculated by those skilled in the art based on multiple sets of fingerprint feature data recorded from historical abnormal electrical equipment, and after normalizing the multiple sets of fingerprint feature data. The normalization process is the same as that for harmonic feature data, and will not be elaborated further here. The fingerprint feature data is pre-stored in a harmonic fingerprint database, which can be an SQL database or a NoSQL database.

[0127] In another preferred embodiment, the method for determining whether to mark an electrical device as having abnormal second harmonic power consumption further includes:

[0128] Multiple sets of fingerprint feature data recorded by historical electricity theft devices are pre-stored in the harmonic fingerprint database to form matching templates;

[0129] The matching template is: device type - harmonic component amplitude - harmonic distortion rate - harmonic duration.

[0130] Harmonic feature data and fingerprint feature data are matched for similarity to obtain similarity values;

[0131] A preset similarity threshold is set. The similarity value is compared with the preset similarity threshold. If the similarity value is greater than or equal to the preset similarity threshold, the electrical equipment is marked as having abnormal second harmonic power consumption. If the similarity value is less than the preset similarity threshold, no action is taken on the electrical equipment.

[0132] It should be noted that the similarity value is calculated using either the cosine similarity algorithm or the Euclidean distance algorithm.

[0133] Step 4: Obtain long-term monitoring data based on electrical parameter data stream, analyze the long-term monitoring data, and determine whether to mark the electrical equipment as having long-term abnormal power consumption;

[0134] It should be noted that the long-term monitoring data includes active power, reactive power, and power factor.

[0135] Please see Figure 3 As shown, the methods for analyzing long-term monitoring data in practice include:

[0136] Step c1: Extract the long-term load factor from the historical load monitoring process and mark it as the historical long-term load factor. Use the extracted historical long-term load factor to establish a load time series set. The load time series set includes i historical long-term load factors. The time interval between the collection of the i historical long-term load factors is equal. The i historical long-term load factors correspond to a long-term analysis period. The reference value for the duration of the long-term analysis period is 1 hour to 30 days.

[0137] The long-term analysis period can be hours or days, or it can be set by those skilled in the art based on practical experience, and no specific limitation is made here.

[0138] It should be noted that the method for obtaining the long-term load factor includes:

[0139] The long-term load factor is obtained by formulating the calculation of active power, reactive power, and power factor from long-term monitoring data. The calculation formula is as follows:

[0140]

[0141] In the formula, CFX represents the long-term load factor, and W represents reactive power. Reactive power W reflects the reactive component generated by electrical energy in electrical equipment, which is usually caused by inductive or capacitive loads.

[0142] Step c2: Input the historical long-term load factor from the load time series set into the load forecasting model to predict the long-term load factor at time T in the future;

[0143] The training method for the load prediction model includes:

[0144] Those skilled in the art, based on practical experience, preset the sliding step size and sliding window length; transform the historical long-term load coefficients within the load time series set into multiple training samples using the sliding window method; use the training samples as input to the recurrent neural network model; predict the long-term load coefficient after the sliding step size as the output; use the subsequent long-term load coefficient of each training sample as the prediction target; use a preset accuracy as the training target to train the recurrent neural network model; after training, obtain the load prediction model; predict the long-term load coefficient at time T in the future based on the historical long-term load coefficients within the load time series set; wherein, the recurrent neural network model can be an RNN neural network model;

[0145] In practice, methods for determining whether to mark electrical equipment as having long-term abnormal power consumption include:

[0146] Step d1: Calculate the predicted long-term load factor CFX at time T in the future. t+1 Compare with the preset load factor threshold FX;

[0147] To further clarify, the long-term load factor predicted by the load forecasting model at time T is the long-term load factor that has not actually occurred. In this case, the long-term load factor at time T is retrieved and denoted as CFX. t+1 A preset load factor threshold is set and marked as FX;

[0148] Step d2: Determine whether to mark the electrical equipment at time T in the future;

[0149] If CFX t+1 If the value is ≥FX, then the electrical equipment at time T in the future will be marked as having long-term abnormal power consumption.

[0150] If CFX t+1 If the value is less than FX, then no action will be taken on the electrical equipment at time T, and monitoring of the electrical equipment at time T will continue.

[0151] Step d3: Based on the long-term abnormal electricity consumption records, long-term abnormal electrical parameter values ​​and long-term timestamps.

[0152] It should be noted that the long-term abnormal electrical parameter values ​​refer to the active power, reactive power, and power factor data related to abnormal behavior of electrical equipment recorded during long-term monitoring and analysis.

[0153] Step 5: Based on short-term abnormal power consumption, harmonic abnormal power consumption, and long-term abnormal power consumption, obtain abnormal characteristic data, and input the abnormal characteristic data into the pre-built abnormal power consumption analysis model to obtain analysis results;

[0154] The abnormal feature data includes short-term timestamps and abrupt electrical parameter values ​​of short-term abnormal electricity consumption records, harmonic abnormal electrical parameter values ​​and harmonic timestamps of harmonic abnormal electricity consumption records, and long-term abnormal electrical parameter values ​​and long-term timestamps of long-term abnormal electricity consumption records; the analysis results include electricity theft, abnormal electricity consumption, equipment failures, and line failures.

[0155] In implementation, the training method for the abnormal power consumption analysis model includes:

[0156] K sets of abnormal feature data are collected in advance, where K is an integer greater than 1. Corresponding prediction results are set for the abnormal feature data. Different letter labels are set for abnormal electricity use, equipment failure, and line failure. For example, abnormal electricity use is labeled Z1, equipment failure is labeled Z2, and line failure is labeled Z3. The prediction results corresponding to the abnormal feature data are obtained by those skilled in the art during the historical abnormal feature data diagnosis process. Those skilled in the art set the corresponding prediction results for the K sets of different abnormal feature data in sequence according to the actual situation.

[0157] The letter labels of the prediction results are marked as prediction labels, and the abnormal feature data and the corresponding prediction labels are converted into a set of feature vectors.

[0158] Each set of feature vectors is used as input to the abnormal power consumption analysis model. The abnormal power consumption analysis model outputs a set of predicted labels corresponding to each set of abnormal feature data and uses the actual predicted labels corresponding to each set of abnormal feature data as the prediction target. The actual predicted labels are the pre-set predicted labels corresponding to the abnormal feature data. The training objective is to minimize the sum of prediction errors of all abnormal feature data. The abnormal power consumption analysis model is trained until the sum of prediction errors converges and then training stops. The abnormal power consumption analysis model is specifically a deep neural network model.

[0159] It is worth noting that the judgment rules for using different letter labels for electricity theft, abnormal electricity use, equipment malfunction, and line fault include:

[0160] During short-timestamp analysis, if there is a sudden increase in current, a slight drop in voltage, and a significantly low power factor within a short timestamp, it is determined that there is abnormal electricity theft behavior.

[0161] If the current suddenly decreases and the voltage slightly increases within a short time stamp, it is determined that there is a fault in the electrical equipment (such as the load suddenly disconnecting or the equipment abnormally disconnecting from operation).

[0162] During harmonic timestamp analysis, if the total harmonic distortion rate significantly exceeds the normal threshold within the harmonic timestamp, and the amplitude of specific harmonics (such as the 3rd and 5th harmonics) increases significantly, it is determined that there is a device used for electricity theft.

[0163] If the harmonic anomaly persists for a long time, it indicates equipment damage or power grid quality problems. Further analysis of the cause is necessary to determine whether it is an equipment failure or a line failure.

[0164] During long-term timestamp analysis, if the long-term load factor is close to or equal to the preset first coefficient threshold within the long-term timestamp, and the low power factor operation time is too long, it is determined that there is abnormal electricity theft behavior (such as illegal loads operating inefficiently for a long time).

[0165] If the load curve suddenly shows obvious abnormalities (such as current and voltage fluctuations that do not match the load pattern), it is determined that there may be a line fault (such as line aging or sudden damage).

[0166] This embodiment acquires electrical parameter data streams such as current, voltage, active power, and reactive power of electrical equipment, and combines this with multi-level analysis including instantaneous detection, harmonic detection, and long-term monitoring to quickly and accurately identify different types of abnormal electricity consumption behaviors. Instantaneous detection can analyze instantaneous current, voltage rate, and power factor in real time through a sliding window to quickly identify short-term abnormal electricity consumption; harmonic detection, based on Fast Fourier Transform and harmonic feature analysis, can effectively capture harmonic anomalies caused by connected electricity theft devices; long-term monitoring combines historical load data and predictive models to provide early warnings of potential long-term abnormal electricity consumption problems. Through multi-dimensional detection methods, this method can not only identify electricity theft but also accurately classify equipment faults and line faults, improving the comprehensiveness and reliability of abnormal electricity consumption analysis.

[0167] This implementation can extract high-dimensional features from multiple sets of abnormal electrical parameter data to complete the classification task of abnormal electricity consumption in complex scenarios. During model training, it combines the timestamps and abrupt changes in electrical parameters of short-term abnormal records, the distortion rate and duration of harmonic abnormal records, and the load coefficient of long-term abnormal records to form a comprehensive feature vector, significantly improving the accuracy and robustness of the analysis. Furthermore, based on the harmonic features and matching templates of historical electricity theft behavior, the abnormal electricity consumption analysis model can further optimize the classification results through similarity determination methods, ensuring the high efficiency of electricity theft behavior identification. This method not only improves the intelligence level of abnormal electricity consumption detection but also continuously optimizes the prediction effect through model training, achieving automated and accurate analysis of abnormal electricity consumption.

[0168] Example 2

[0169] Please see Figure 4 As shown, this embodiment provides an electrical anomaly detection device based on dynamic tracking of electrical parameters. The device includes a data acquisition module, an instantaneous detection module, a harmonic detection module, a long-term detection module, and a comprehensive analysis module. The modules are connected via wired and / or wireless means to realize data transmission between the modules.

[0170] The data acquisition module acquires the electrical parameter data stream of the nth electrical device in the target area. The electrical parameter data stream includes current value, voltage value, active power and reactive power.

[0171] The instantaneous detection module acquires instantaneous detection data based on electrical parameter data streams, analyzes the instantaneous detection data, and determines whether to mark the electrical equipment as having short-term abnormal power consumption.

[0172] The harmonic detection module acquires harmonic detection data based on electrical parameter data streams, analyzes the harmonic detection data, and determines whether to mark the electrical equipment as having abnormal harmonic power consumption.

[0173] The long-term monitoring module acquires long-term monitoring data based on electrical parameter data streams, analyzes the long-term monitoring data, and determines whether to mark the electrical equipment as having long-term abnormal power consumption.

[0174] The comprehensive analysis module obtains abnormal characteristic data based on short-term abnormal power consumption, harmonic abnormal power consumption, and long-term abnormal power consumption. The abnormal characteristic data is then input into a pre-built abnormal power consumption analysis model to obtain analysis results.

[0175] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0176] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for detecting abnormal electricity consumption based on dynamic tracking of electrical parameters, characterized in that, include: Acquire the electrical parameter data stream of the nth electrical device within the target area, wherein the electrical parameter data stream includes current value, voltage value, active power and reactive power; Instantaneous detection data is acquired based on electrical parameter data streams, and the instantaneous detection data is analyzed to determine whether to mark the electrical equipment as having short-term abnormal power consumption. Harmonic detection data is acquired based on electrical parameter data streams, and the harmonic detection data is analyzed to determine whether to mark electrical equipment as having abnormal harmonic power consumption. Long-term monitoring data is acquired based on electrical parameter data streams, and the long-term monitoring data is analyzed to determine whether to mark the electrical equipment as having long-term abnormal power consumption. Abnormal power consumption characteristics data are obtained based on short-term abnormal power consumption, harmonic abnormal power consumption, and long-term abnormal power consumption. The abnormal characteristic data are then input into a pre-built abnormal power consumption analysis model to obtain analysis results. The instantaneous detection data includes instantaneous voltage, instantaneous current, and power factor; Methods for analyzing instantaneous detection data include: Step a1: Calculate the instantaneous current rate using a sliding window. Instantaneous voltage rate and real-time power factor ; Step a2: Set the instantaneous current rate threshold Instantaneous voltage rate threshold and power factor lower limit threshold ; Instantaneous current rate With instantaneous current rate threshold For comparison, instantaneous voltage rate With instantaneous voltage rate threshold For comparison, real-time power factor power factor lower limit threshold Compare; like and and If so, the current electrical equipment will be marked as having short-term abnormal power consumption; like and and If so, no action will be taken on the current electrical equipment; Step a3: Based on the short-term abnormal power consumption record, record the short-term timestamp and the sudden change in electrical parameter value.

2. The method for detecting abnormal electricity consumption based on dynamic tracking of electrical parameters according to claim 1, characterized in that, Harmonic detection data includes current, voltage values, and harmonic distortion rate; The abnormal harmonic power consumption includes the first abnormal harmonic power consumption and the second abnormal harmonic power consumption; Methods for analyzing harmonic detection data based on harmonic analysis include: Step b1: Perform spectral analysis on the current value using Fast Fourier Transform to extract the harmonic component amplitudes. ; Step b2: Based on the harmonic component amplitude Calculate harmonic distortion rate ; Step b3: Set a preset distortion rate threshold. Compare the harmonic distortion rate with the preset distortion rate threshold. If the harmonic distortion rate is greater than or equal to the preset distortion rate threshold, mark the electrical equipment as having abnormal first harmonic power consumption. If the harmonic distortion rate is less than the preset distortion rate threshold, generate an analysis command. Step b4: Receive the analysis command, obtain the harmonic characteristic coefficient, compare the harmonic characteristic coefficient with the preset first coefficient threshold, and determine whether to mark the electrical equipment as having abnormal second harmonic power consumption. Step b5: Record the abnormal electrical parameters and timestamps of the harmonics based on the abnormal power consumption of the first or second harmonic.

3. The method for detecting abnormal electricity consumption based on dynamic tracking of electrical parameters according to claim 2, characterized in that, Methods for obtaining harmonic characteristic coefficients include: Step b41: Obtain harmonic characteristic data, which includes harmonic component amplitude, harmonic distortion rate, and harmonic duration; Step b42: Normalize the harmonic characteristic data and calculate the harmonic characteristic coefficients. .

4. The method for detecting abnormal electricity consumption based on dynamic tracking of electrical parameters according to claim 3, characterized in that, Methods for determining whether to mark electrical equipment as having abnormal second harmonic power consumption include: If the harmonic characteristic coefficient is greater than or equal to the preset first coefficient threshold, the electrical equipment will be marked as having abnormal second harmonic power consumption. If the harmonic characteristic coefficient is less than the preset first coefficient threshold, no action will be taken on the electrical equipment.

5. The method for detecting abnormal electricity consumption based on dynamic tracking of electrical parameters according to claim 3, characterized in that, The method for obtaining the harmonic duration includes: Set the harmonic distortion rate threshold, when When the harmonic distortion rate is greater than or equal to the set harmonic distortion rate threshold, the recording start time is... ,when When the harmonic distortion rate is less than the set threshold, the recording ends at [time]. ; Calculate the duration of harmonics ; Methods for determining whether to mark electrical equipment as having abnormal second harmonic power consumption also include: Multiple sets of fingerprint feature data recorded by historical electricity theft devices are pre-stored in the harmonic fingerprint database to form matching templates; The matching template is: device type - harmonic component amplitude - harmonic distortion rate - harmonic duration; Harmonic feature data and fingerprint feature data are matched for similarity to obtain similarity values; A preset similarity threshold is set. The similarity value is compared with the preset similarity threshold. If the similarity value is greater than or equal to the preset similarity threshold, the electrical equipment is marked as having abnormal second harmonic power consumption. If the similarity value is less than the preset similarity threshold, no action is taken on the electrical equipment.

6. The method for detecting abnormal electricity consumption based on dynamic tracking of electrical parameters according to claim 5, characterized in that, The long-term monitoring data includes active power, reactive power, and power factor; Methods for analyzing long-term monitoring data include: Step c1: Extract the long-term load factor from the historical load monitoring process and mark it as the historical long-term load factor. Use the extracted historical long-term load factor to establish a load time series set. The load time series set includes i historical long-term load factors. The time interval of the i historical long-term load factors is equal. The i historical long-term load factors correspond to a long-term analysis period. The method for obtaining the long-term load factor includes: The active power, reactive power, and power factor from long-term monitoring data are calculated using formulas to obtain the long-term load factor. ; Step c2: Input the historical long-term load factor from the load time series set into the load forecasting model to predict the long-term load factor at time T in the future.

7. The method for detecting abnormal electricity consumption based on dynamic tracking of electrical parameters according to claim 6, characterized in that, Methods for determining whether to mark electrical equipment as having long-term abnormal power consumption include: Step d1: Calculate the predicted long-term load factor at time T. With preset load factor threshold Compare; Step d2: Determine whether to mark the electrical equipment at time T in the future; like Then, the electrical equipment at time T in the future will be marked as having long-term abnormal power consumption; like If so, no action will be taken on the electrical equipment at time T in the future, and monitoring of the electrical equipment at time T in the future will continue; Step d3: Based on the long-term abnormal electricity consumption records, long-term abnormal electrical parameter values ​​and long-term timestamps.

8. The method for detecting abnormal electricity consumption based on dynamic tracking of electrical parameters according to claim 7, characterized in that, The abnormal feature data includes short-term timestamps and abrupt electrical parameter values ​​of short-term abnormal electricity consumption records, harmonic abnormal electrical parameter values ​​and harmonic timestamps of harmonic abnormal electricity consumption records, and long-term abnormal electrical parameter values ​​and long-term timestamps of long-term abnormal electricity consumption records. The analysis results include electricity theft, abnormal electricity use, equipment malfunctions, and line faults. The training method for the abnormal power consumption analysis model includes: K sets of abnormal feature data are collected in advance, where K is an integer greater than 1. The corresponding prediction results are set for the abnormal feature data. Different letter labels are set for abnormal electricity use, equipment failure and line failure. The letter labels of the prediction results are marked as prediction labels. The abnormal feature data and the corresponding prediction labels are converted into a set of feature vectors. Each set of feature vectors is used as input to the abnormal power consumption analysis model. The abnormal power consumption analysis model outputs a set of predicted labels corresponding to each set of abnormal feature data and uses the actual predicted labels corresponding to each set of abnormal feature data as the prediction target. The actual predicted labels are the pre-set predicted labels corresponding to the abnormal feature data. The training objective is to minimize the sum of prediction errors of all abnormal feature data. The abnormal power consumption analysis model is trained until the sum of prediction errors converges and then training stops. The abnormal power consumption analysis model is a deep neural network model.

9. A power consumption anomaly detection device based on dynamic tracking of electrical parameters, used to implement the power consumption anomaly detection method based on dynamic tracking of electrical parameters as described in any one of claims 1-8, characterized in that, include: The data acquisition module acquires the electrical parameter data stream of the nth electrical device in the target area. The electrical parameter data stream includes current value, voltage value, active power and reactive power. The instantaneous detection module acquires instantaneous detection data based on electrical parameter data streams, analyzes the instantaneous detection data, and determines whether to mark the electrical equipment as having short-term abnormal power consumption. The harmonic detection module acquires harmonic detection data based on electrical parameter data streams, analyzes the harmonic detection data, and determines whether to mark the electrical equipment as having abnormal harmonic power consumption. The long-term monitoring module acquires long-term monitoring data based on electrical parameter data streams, analyzes the long-term monitoring data, and determines whether to mark the electrical equipment as having long-term abnormal power consumption. The comprehensive analysis module obtains abnormal characteristic data based on short-term abnormal power consumption, harmonic abnormal power consumption, and long-term abnormal power consumption. The abnormal characteristic data is then input into a pre-built abnormal power consumption analysis model to obtain analysis results.

Images